scholarly journals A RESTful middleware for AI controlled sensors, actuators and smart devices

2019 ◽  
Vol 11 (7) ◽  
pp. 2963-2986 ◽  
Author(s):  
Nikos Dipsis ◽  
Kostas Stathis

Abstract The numerous applications of internet of things (IoT) and sensor networks combined with specialized devices used in each has led to a proliferation of domain specific middleware, which in turn creates interoperability issues between the corresponding architectures and the technologies used. But what if we wanted to use a machine learning algorithm to an IoT application so that it adapts intelligently to changes of the environment, or enable a software agent to enrich with artificial intelligence (AI) a smart home consisting of multiple and possibly incompatible technologies? In this work we answer these questions by studying a framework that explores how to simplify the incorporation of AI capabilities to existing sensor-actuator networks or IoT infrastructures making the services offered in such settings smarter. Towards this goal we present eVATAR+, a middleware that implements the interactions within the context of such integrations systematically and transparently from the developers’ perspective. It also provides a simple and easy to use interface for developers to use. eVATAR+ uses JAVA server technologies enhanced by mediator functionality providing interoperability, maintainability and heterogeneity support. We exemplify eVATAR+ with a concrete case study and we evaluate the relative merits of our approach by comparing our work with the current state of the art.

2018 ◽  
Vol 108 (05) ◽  
pp. 319-324
Author(s):  
I. Bogdanov ◽  
A. Nuffer ◽  
A. Sauer

Der vorliegende Beitrag behandelt den Themenkomplex Ressourcen-effizienz und digitale Transformation im verarbeitenden Gewerbe sowie die dabei entstehenden Wechselwirkungen. Neben dem aktuellen Stand der Technik werden die im Rahmen einer aktuellen Studie durchgeführte Fallbeispielanalyse und die entwickelte Methodik zur Ermittlung der Ressourceneffizienzpotenziale vorgestellt. Diese Potenziale und die eingesetzten digitalen Maßnahmen sind zentrale Bausteine des vorliegenden Beitrags.   This article deals with the topic complex of resource efficiency and digital transformation in the manufacturing sector as well as the resulting interactions. In addition to the current state of the art and perspectives, the case study analysis carried out as part of a current study, as well as the developed method for establishing the resource efficiency potentials will be presented. The resultant potential and the digital measures are central components of this article.


Author(s):  
Pushpak Bhattacharyya ◽  
Mitesh Khapra

This chapter discusses the basic concepts of Word Sense Disambiguation (WSD) and the approaches to solving this problem. Both general purpose WSD and domain specific WSD are presented. The first part of the discussion focuses on existing approaches for WSD, including knowledge-based, supervised, semi-supervised, unsupervised, hybrid, and bilingual approaches. The accuracy value for general purpose WSD as the current state of affairs seems to be pegged at around 65%. This has motivated investigations into domain specific WSD, which is the current trend in the field. In the latter part of the chapter, we present a greedy neural network inspired algorithm for domain specific WSD and compare its performance with other state-of-the-art algorithms for WSD. Our experiments suggest that for domain-specific WSD, simply selecting the most frequent sense of a word does as well as any state-of-the-art algorithm.


2020 ◽  
Vol 10 (1) ◽  
pp. 1-12
Author(s):  
Noura A. AlSomaikhi ◽  
Zakarya A. Alzamil

Microblogging platforms, such as Twitter, have become a popular interaction media that are used widely for different daily purposes, such as communication and knowledge sharing. Understanding the behaviors and interests of these platforms' users become a challenge that can help in different areas such as recommendation and filtering. In this article, an approach is proposed for classifying Twitter users with respect to their interests based on their Arabic tweets. A Multinomial Naïve Bayes machine learning algorithm is used for such classification. The proposed approach has been developed as a web-based software system that is integrated with Twitter using Twitter API. An experimental study on Arabic tweets has been investigated on the proposed system as a case study.


Author(s):  
Esteban Real ◽  
Alok Aggarwal ◽  
Yanping Huang ◽  
Quoc V. Le

The effort devoted to hand-crafting neural network image classifiers has motivated the use of architecture search to discover them automatically. Although evolutionary algorithms have been repeatedly applied to neural network topologies, the image classifiers thus discovered have remained inferior to human-crafted ones. Here, we evolve an image classifier— AmoebaNet-A—that surpasses hand-designs for the first time. To do this, we modify the tournament selection evolutionary algorithm by introducing an age property to favor the younger genotypes. Matching size, AmoebaNet-A has comparable accuracy to current state-of-the-art ImageNet models discovered with more complex architecture-search methods. Scaled to larger size, AmoebaNet-A sets a new state-of-theart 83.9% top-1 / 96.6% top-5 ImageNet accuracy. In a controlled comparison against a well known reinforcement learning algorithm, we give evidence that evolution can obtain results faster with the same hardware, especially at the earlier stages of the search. This is relevant when fewer compute resources are available. Evolution is, thus, a simple method to effectively discover high-quality architectures.


Author(s):  
Kevin R. Anderson ◽  
Wael Yassine

Abstract This paper presents modeling of the Puna Geothermal Venture as a case study in understanding how the technology of geothermal can by successfully implemented. The paper presents a review of the Puna Geothermal Venture specifications, followed by simulation results carried out using NREL SAM and RETSCREEN analysis tools in order to quantify the pertinent metrics associated with the geothermal powerplant by retrofitting its current capacity of 30 MW to 60 MW. The paper closes with a review of current state-of-the art H2S abatement strategies for geothermal power plants, and presents an outline of how these technologies can be implemented at the Puna Geothermal Venture.


Designs ◽  
2018 ◽  
Vol 2 (4) ◽  
pp. 37 ◽  
Author(s):  
Charul Chadha ◽  
Kathryn Crowe ◽  
Christina Carmen ◽  
Albert Patterson

This work explores an additive-manufacturing-enabled combination-of-function approach for design of modular products. AM technologies allow the design and manufacturing of nearly free-form geometry, which can be used to create more complex, multi-function or multi-feature parts. The approach presented here replaces sub-assemblies within a modular product or system with more complex consolidated parts that are designed and manufactured using AM technologies. This approach can increase the reliability of systems and products by reducing the number of interfaces, as well as allowing the optimization of the more complex parts during the design. The smaller part count and the ability of users to replace or upgrade the system or product parts on-demand should reduce user risk, life-cycle costs, and prevent obsolescence for the user of many systems. This study presents a detailed review on the current state-of-the-art in modular product design in order to demonstrate the place, need and usefulness of this AM-enabled method for systems and products that could benefit from it. A detailed case study is developed and presented to illustrate the concepts.


2020 ◽  
Vol 34 (10) ◽  
pp. 13833-13834
Author(s):  
Anish Kachinthaya ◽  
Yi Ding ◽  
Tobias Hollerer

In this paper, we look at how depth data can benefit existing object masking methods applied in occluded scenes. Masking the pixel locations of objects within scenes helps computers get a spatial awareness of where objects are within images. The current state-of-the-art algorithm for masking objects in images is Mask R-CNN, which builds on the Faster R-CNN network to mask object pixels rather than just detecting their bounding boxes. This paper examines the weaknesses Mask R-CNN has in masking people when they are occluded in a frame. It then looks at how depth data gathered from an RGB-D sensor can be used. We provide a case study to show how simply applying thresholding methods on the depth information can aid in distinguishing occluded persons. The intention of our research is to examine how features from depth data can benefit object pixel masking methods in an explainable manner, especially in complex scenes with multiple objects.


Sign in / Sign up

Export Citation Format

Share Document